EP3714337A1 - Simulieren von statistisch modellierten sensordaten - Google Patents
Simulieren von statistisch modellierten sensordatenInfo
- Publication number
- EP3714337A1 EP3714337A1 EP19720390.4A EP19720390A EP3714337A1 EP 3714337 A1 EP3714337 A1 EP 3714337A1 EP 19720390 A EP19720390 A EP 19720390A EP 3714337 A1 EP3714337 A1 EP 3714337A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- sensor data
- simulated
- training
- model
- rsd
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B17/00—Systems involving the use of models or simulators of said systems
- G05B17/02—Systems involving the use of models or simulators of said systems electric
Definitions
- the invention relates to a sensor data simulation device. Furthermore, the invention relates to a training device. Moreover, the invention relates to a method for emulating sensor data. Moreover, the invention relates to a training procedure for training a sensor data simulation tions V orraum.
- Snow or even snow during a scheduled test run is present, when the functionality of a sensor with weather conditions, such as snow, is correlated.
- the sensor data simulation device has a physics engine for generating first simulated sensor data based on a physical model.
- a physical model describes a mathematical relationship between different physical quantities.
- the method according to the invention involves a mathematical description of the relationship between physical quantities which describe the environmental influences on a sensor in question and physical variables characterizing the sensor and its response behavior.
- Such a physical model can be generated, for example, by a physics engine.
- the physics engine also considers constraints and constraints in its applied model equations. For example, the thickness of lines and the length of the lines is ge used to calculate a heat loss.
- Part of the inventive sensor data simulation device is also a statistical model unit for generating second simulated sensor data based on a trained statistical model, which was obtained by training with real sensor data and is adapted to reproduce the time-dependent statistical behavior of the real sensor data.
- a trained statistical model should in this context include a statistical model which is generated on the basis of a learning algorithm, for example a machine learning method.
- a statistical model should be understood as a model which The temporal variability of the sensor values is statistically described.
- the sensor data simulation device By model-taking into account the statistical behavior of the sensor data by learning from real sensor data, the sensor data simulation device according to the invention can be used to generate simulated sensor data which has a certain complementarity with the data of the physical model. In this way, more accurate sensor data can be generated over a larger parameter range. In addition, a thorough acquisition of real test data by the simulation can be reduced.
- the training device comprises a first interface for receiving second simulated sensor data, which are generated with a statistical model to be trained, and a model training unit for training the statistical model with real sensor data and the second simulated sensor data received via the first interface.
- the statistical model can be adapted to changing conditions, which affects the response behavior of the sensors and the environmental conditions.
- first simulated sensor data are generated on the basis of a physical model.
- second simulated sensor data are generated on the basis of the trained statistical model.
- the trained statistical model was obtained in a previous training process by training with real sensor data and reflects the time-dependent statistical behavior of the real sensor data.
- the method according to the invention shares the advantages of the sensor data simulation device according to the invention.
- the first simulated sensor data are generated on the basis of the physical model. Furthermore, a statistical model with real sensor data is trained. In addition, second simulated sensor data is generated using the trained statistical model.
- Parts of the sensor data simulation device according to the invention and of the training device can for the most part be designed in the form of software components. This applies in particular to parts of the physics engine, the statistical model unit and the model training unit. In principle, these components but also in part, in particular when it comes to very fast calculations, in the form of software-supported hardware, such as FPGAs or the like, be realized.
- the required interfaces for example, if it is only about an acquisition of data from other software components, be designed as software interfaces. However, they can also be configured as hardware-based interfaces, which are controlled by suitable software.
- a partial software realization has the advantage that even previously used for sensor data simulation computer systems can be retrofitted in a simple way by a software update to work in the inventive way.
- the problem is also solved by a corresponding computer program product with a computer program. solved, which directly in a memory device ei nes such a computer system is loadable, with Programmabschnit th to perform all steps of the method for simulating Sen sor songs and / or the training method for training the sensor data simulation device according to the invention trainees, if the computer program in the computer system is performed.
- Such a computer program product may, in addition to the computer program, optionally contain additional components, such as e.g. a documentation and / or additional components, also hardware components, such as e.g. Hardware keys (dongles, etc.) for using the software include
- a compu terlesbares medium such as a memory stick, a hard disk or other portable or fixed Clarker disk serve, on which the unit readable by a computer and executable program sections of the computer program are stored.
- the computer unit may e.g. For this purpose, one or more cooperating Mikropro processors or the like.
- the sensor data simulation device preferably also comprises a fusion unit for generating a set of combined simulated sensor data by combining the first simulated sensor data with the second sensor data.
- a fusion unit for generating a set of combined simulated sensor data by combining the first simulated sensor data with the second sensor data.
- a trained combination model is a model to be understood, which generates based on a learning algorithm, example, a machine learning method, combined simulated sensor data.
- the learning process is virtually a two-stage learning process.
- For the training of the combination algorithm initially second simulated sensor data is needed, which in turn were model-based or generated based on a learning algorithm using real sensor data as test data.
- the sensor data generated as part of the learning process by combination can then be used in the context of a matching process together with the test data to adapt the learning algorithm.
- the trained statistical model reproduces the dynamic behavior of the sensor, of which real sensor data were used to train the statistical model.
- the time-dependent statistically describable behavior of the sensor By taking into account the time-dependent statistically describable behavior of the sensor, more realistic simulated sensor data are obtained. similar to conventional simulated by a physics engine sensor data.
- the statistical model simulates the noise behavior of the sensor and / or artifacts generated by the sensor whose real sensor data was used to train the statistical model.
- the actual response behavior of a sensor can be particularly accurately simulated.
- the physical model when training the statistical model, takes into account collected metadata concerning the environmental conditions in the generation of the genuine sensor data when generating the first simulated sensor data.
- the physical model can be made more precise knowing specific values of the metadata.
- the trained statistical model was generated by training real sensor data to which different values of metadata are assigned.
- values of metadata can also be taken into account when training the statistical model, so that the statistical model can be made even more precise and particularly realistic simulated second sensor data can be generated.
- the metadata comprise at least one of the following types of data:
- the sensor state should in this context include the current physical state of the sensor, which includes for example the supply voltage, the current intensity and the Sen s temperature.
- the sensor state also includes different modes in which a sensor can be operated.
- the travel metadata includes the place of departure, the place of arrival and the timetable data.
- the information mentioned influences the response behavior of a sensor. It is thus advantageous to take this data into account in the generation of simulated sensor data, in order to achieve a more sophisticated simulation which is better adapted to the reality.
- the training device preferably has a combination modeling training unit for training the combination model on the basis of real sensor data and the simulated first and second sensor data.
- the two models le, i. the statistical model and the combination model can be trained together with each other simultaneously, but they can also be trained independently of each other.
- the combination algorithm of the simulated sensor data generated on the basis of different models is advantageously adaptable to specific conditions by the combination model training unit.
- the sensor data simulation device has the training device according to the invention.
- parts of the sensor data simulation device such as the physics engine, the statistical model unit, and the fusion unit, can also be used use for the training process, so that in a direct interaction of the two devices according to the invention these elements are needed only once.
- a set of combined simulated sensor data is preferably simulated by combining the first simulated sensor data with the second simulated sensor data using the trained combination model on the first simulated sensor data and the second simulated sensor data gained sensor data.
- the trained combination model was obtained in a previous training process by training with real sensor data and simulated first and second sensor data.
- the combina tion process is based on a trained cherrysmo model, which is customizable to different training data sets customizable.
- the combination model is trained with the real sensor data and the simulated first and second sensor data.
- the combination of the simulated sensor data is also included in the training process, so that particularly realistic sensor data can be simulated.
- Machine learning in contrast to a rigid model, can be adapted much more flexibly and precisely to scenarios that are either inadequate or wall or not at all by a physical model be writable.
- a statistical component is extracted from the real sensor data, and the sequential statistical model is trained on the basis of the statistical component, whereby the time-dependent behavior of the statistical component is learned becomes.
- a sequential statistical model is used to model sequences of events. Examples include the hidden Markov model or recurrent neural networks.
- the extraction of the statistical component by applying a time derivative and / or a high-pass filter to the real sensor data.
- noise components can be separated from sensor data.
- the sequential statistical model comprises the technique of long short-term memory (referred to as “long short term memory”, abbreviated LSTM).
- 1 shows a schematic representation of a sensor data simulation device according to an embodiment of the invention
- 2 shows a flowchart which illustrates a method for simulating sensor data according to an exemplary embodiment of the invention
- FIG. 3 is a flow chart illustrating a training method for training the models used in the method illustrated in FIG. 2 according to an embodiment of the invention.
- FIG. 4 shows a flow chart, which illustrates a training method according to an embodiment of the invention.
- a sensor data simulation device 10 according to an embodiment of the invention is shown schematically Darge.
- the sensor data simulation device 10 has a simulation component 10 a and a training device 20.
- the simulation component 10a a model simulation of sensor data KSSD is performed.
- the training device 20 serves to generate models STM, KM based on a real learning method based on real sensor data RSD.
- KM a statistical model STM and a combination model KM, are used to generate simulated sensor data SSD2, KSSD for specific sensors and are stored after their generation by the training device 20 in a sensor model database SMDB or in a combination model database KMDB, each part of the simulation component 10a.
- the simulation component 10a includes a physics engine 11 configured to generate first simulated sensor data SSD1 based on a physical model for a specific sensor. Part of the simulation component 10a is also a statistical model unit 12, which is equipped to generate second simulated sensor data SSD2 on the basis of a trained statistical model STM.
- the trained statistical model which is specific for a particular sensor, is stored in the already mentioned sensor model database SMDB and can, if required, ie if a sensor data simulation for a specific sensor is to be transmitted from this sensor model database SMDB to the statistical model unit 12.
- the statistical model STM was obtained by training with real sensor data RSD of a respective sensor and reflects the time-dependent statistical behavior of the real sensor data.
- Part of the simulation component 10a is also a fusion unit 13 which is connected to the physics engine 11 and the statistical model unit 12 via communication channels and from these the first simulated sensor data SSD1 and the second simulated sensor data SSD2, which for example simulated noise components or simulated artifacts include, receives.
- the fusion unit 13 is configured to generate a set of combined simulated sensor data KSSD by combining the first simulated sensor data SSD1 with the second simulated sensor data SSD2.
- the combining operation finds the first simulated sensor data SSD1 and the second simulated sensor data SSD2 using a combination model KM trained by a machine learning method.
- the case used te trained combination model KM was using the Trai ningsvorraum 20 by training with real sensor data RSD and simulated first and second sensor data SSD1, SSD2 won.
- the generated combined simulated sensor data KSSD can be output via an output interface 14, which is also part of the simulation component 10a.
- the fusion unit 13 represents an optional feature and also embodiments without a fusion unit 13 are meaningful and executable.
- the training device 20 has a statistical model training unit 22 and a combination model training unit 24.
- the model training unit 22 is used to train a statistical model STM for a particular sensor with ech th sensor data RSD using a machine Lernverfah rens.
- the statistical model training unit 22 has a model adaptation unit 22a and a comparison unit 22b.
- the model adaptation unit 22a first generates an initial it model STM of a specific sensor or Behhal least and transmits this model STM to the already mentioned statistic statistical model unit 12, which generates second simulated sensor data SSD2 based on the obtained model STM, and also to the comparison unit 22b.
- the second simulated sensor data SSD2 are averaged as part of the machine learning process to the comparison unit 22b, which performs a so-called matching process in which noise components STK afflicted genuine sen sordata RSD, which are stored in the test database TDB, with the adjusted second simulated sensor data SSD2. If it was determined during the matching process that the generated sensor data SSD2 sufficiently coincide with the real sensor data RSD or the matching process has a positive result, the statistical model STM transmitted last to the comparison unit 22b is stored in the sensor model database SMDB. Otherwise, depending on the result of the matching process, correction parameters KD are transmitted to the model matching unit 22a.
- the model adaptation unit 22a then generates a corrected statistical model STM in dependence on the correction parameters KD obtained and in turn transmits this model STM to the statistical model unit 12 as well as to the comparison unit 22b.
- the statistical model unit 12 then again generates second simulated sensor data SSD2, which in turn is subjected by the comparison unit 22b to a matching process with the genuine sensor data RSD. The described process is carried out further until the result of the matching process makes no further corrections necessary. Subsequently, the last used statistical model STM is stored in the sensor model database SMDB.
- the combination model training unit 24 has an initialization unit 24a, with the real sensor data RSD received depending on the test database TDB for a specific sensor simulating a first simulated generation Sensor data SSD1 is instructed in the physics engine 11 and a simulation of second simulated sensor data SSD2 in the statistical model unit 12 is instructed ( Kommuni cation lines between the initialization unit 24a and the physics engine 11 and the statistical model unit 12 are not shown for clarity). Furthermore, the combination model training unit 24 has a model adaptation unit 24b, which transmits an initial combination model KM to the combination unit 13 on the basis of genuine sensor data RSD obtained from the test database TDB. The combination unit 13 combines the first and second simulated sensor data SSD1, SSD2 generated for training purposes with each other and transmits the combined simulated sensor data KSSD to a comparison unit 24c, which is also part of the combination model training unit 24.
- the combined simulated sensor data KSSD are transmitted as part of the machine learning process to the comparison unit 24c, which performs a so-called matching process in which real sensor data RSD stored in the test database TDB with the generated combined simulated sensor data KSSD be matched. If it has been determined during the matching process that the combined simulated sensor data KSSD generated by it match sufficiently with the genuine sensor data RSD or
- Matching process correction parameter KD transmitted to the model adaptation unit 24b.
- the model adaptation unit 24b then generates a corrected combination model KM and in turn transmits this model KM to the combination model unit 13 as well as to the comparison unit 24c.
- the combination nation model unit 13 again generates combined simulated sensor data KSSD, which in turn is subjected by the comparison unit 24b to a matching process with the real sensor data RSD. The process described is continued until the result of the matching process makes no further corrections necessary. Subsequently, the last used combination model KM is stored in the combination model database KMDB, in which it is available for simulations.
- a flowchart 200 is shown which illustrates a method for simulating sensor data according to an exemplary embodiment of the invention.
- a plurality of first simulated sensor data SSD1 are generated with the aid of a physics engine for defined sensor parameters and environmental parameters.
- a plurality of second simulated sensor data SSD2 are generated for the same defined sensor parameters and environmental parameters, which are also in the Step 2.1 were used.
- the statistical model STM was obtained by machine learning with real sensor data RSD or on these basing statistical components.
- the second sampled sensor data SSD2 may comprise, for example, a statistical component, such as, for example, noise effects or artifacts, which may occur due to environmental influences or due to design.
- a complete second simulated sensor data SSD2 only the statistical components associated therewith can be generated.
- step 2. III the first and second simulated sensor data SSD1, SSD2 are used to generate a set of combined simulated sensor data KSSD.
- the set of combined simulated sensor data KSSD is obtained by combining the first simulated sensor data SSD1 with the second simulated sensor data SSD2 achieved.
- the combination is done by applying a machine-learning-trained combination model KM that has been trained to generate the first and second sensor data SSD1,
- SSD2 combine with each other so that the combined simulated sensor data KSSD generated in the Kom, as closely as possible correspond to the real sensor used for the training data RSD.
- machine learning methods are used both for generating statistical components of simulated sensor data and additionally for the combination of these simulated statistical components with simulated sensor data, which were generated by a physical model.
- FIG. 3 shows a flowchart 300 which illustrates a training method for training a sensor data simulation device according to an exemplary embodiment of the invention.
- the first statistical sensor data SSD1 for certain defined environmental parameters and sensor parameters is first generated in step 3.1 with a physical model PM, which is realized by a physics engine, wherein the corresponding parameters resp whose values are varied in order to obtain simulated sensor values for a correspondingly broad parameter range.
- the parameter range depends among others on the existing real sensor data RSD or on the parameter value range assigned to it.
- a dynamic statistical model STM is trained by machine learning MLM on the basis of real sensor data RSD.
- the real sensor data RSD can originate, for example, from a test database TDB (see FIG. 1).
- the real sensor data RSD can, for example, statistical, ie statistically varying over time components that are used to train the dynamic statistical model STM.
- the statistical components For example, they can affect the noise behavior of the simulated sensor data.
- step 3. III second simulated sensor data SSD2 are subsequently generated with the aid of the trained statistical model STM.
- the second simulated sensor data SSD2 comprise the described statistical component of sensor data.
- step 3. IV training is then carried out on a combination model KM.
- the combination model KM is intended to suitably combine the first sensor data SSD1 simulated via the physical model and the second sensor data SSD2 mimulated with the statistical model STM, i. in such a way that the combined sensor data KSSD generated by the combination model KM correspond to the real sensor data RSD used for the training, for the specific parameter values associated therewith.
- FIG. 4 shows a flowchart 400 which illustrates a training method for training models for simulating sensor data according to a second exemplary embodiment of the invention.
- step 4.1 as in the embodiment illustrated in FIG. 3, first simulated sensor data SSD1 are generated with the aid of a physics engine or a physical model PM realized by the physics engine.
- RSD noise components STK are extracted in the step 4. II from the real sensor data. The extraction of these noise components STK he follows in the embodiment shown in Figure 4 by applying a high-pass filter on the training process underlying real sensor data RSD.
- the noise components STK are then processed in step 4.III using a sequential statistical model, in this case a model referred to as "short-term long-term memory" KZLZG, with which the noise behavior of the sensor data RSD is automated as a function of time is learned In the step 4.
- the short-term long-term memory KZLZG having noise components STK has been sufficiently trained, it can then be used in step 4.IV to generate simulated noise components SSTK as time series, these simulated noise components SSTK are then used in step 4.V together with the first simulated sensor data SSD1 and the real sensor data RSD are used to machine-learn a combination model KM
- the combination model KM is intended to serve as the first sensor data SSD1 simulated via the physical model PM and Short-term long-term memory "KZLZG designated statistical model simulated noise components SSTK suitable to combinate kidney, ie to combine such that the combined sensor data KSSD generated by the Combi nation model KM correspond to the used for the training real sensor data RSD for the associated parameter values.
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102018205660.9A DE102018205660A1 (de) | 2018-04-13 | 2018-04-13 | Simulieren von statistisch modellierten Sensordaten |
| PCT/EP2019/058785 WO2019197324A1 (de) | 2018-04-13 | 2019-04-08 | Simulieren von statistisch modellierten sensordaten |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| EP3714337A1 true EP3714337A1 (de) | 2020-09-30 |
| EP3714337B1 EP3714337B1 (de) | 2021-10-13 |
Family
ID=66334361
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP19720390.4A Not-in-force EP3714337B1 (de) | 2018-04-13 | 2019-04-08 | Simulieren von statistisch modellierten sensordaten |
Country Status (3)
| Country | Link |
|---|---|
| EP (1) | EP3714337B1 (de) |
| DE (1) | DE102018205660A1 (de) |
| WO (1) | WO2019197324A1 (de) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021194369A1 (en) * | 2020-03-27 | 2021-09-30 | Siemens Schweiz Ag | Computerized device and computer-implemented method for controlling a hvac system |
| DE102022002242A1 (de) | 2022-06-21 | 2023-12-21 | Mercedes-Benz Group AG | Virtueller Sensor und Verfahren zum Betrieb eines virtuellen Sensors |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| ATE326717T1 (de) * | 2002-09-26 | 2006-06-15 | Siemens Ag | Vorrichtung und verfahren zur überwachung einer mehrere systeme umfassenden technischen anlage, insbesondere einer kraftwerksanlage |
| ATE445870T1 (de) * | 2005-12-05 | 2009-10-15 | Siemens Corp Res Inc | Verwendung von sequentiellem clustering zur instanzenauswahl bei der maschinenzustandsüberwachung |
| US7505949B2 (en) * | 2006-01-31 | 2009-03-17 | Caterpillar Inc. | Process model error correction method and system |
| US8095479B2 (en) * | 2006-02-28 | 2012-01-10 | Hitachi, Ltd. | Plant control apparatus and method having functions of determining appropriate learning constraint conditions |
| DE102007059582B4 (de) * | 2007-11-15 | 2010-06-10 | Outotec Oyj | Verfahren und Vorrichtung zum Training des Bedienpersonals einer prozesstechnischen Anlage |
| US10466142B2 (en) * | 2016-07-13 | 2019-11-05 | Hitachi, Ltd. | Equipment control based on failure determination |
| JP6562883B2 (ja) * | 2016-09-20 | 2019-08-21 | 株式会社東芝 | 特性値推定装置および特性値推定方法 |
-
2018
- 2018-04-13 DE DE102018205660.9A patent/DE102018205660A1/de not_active Ceased
-
2019
- 2019-04-08 WO PCT/EP2019/058785 patent/WO2019197324A1/de not_active Ceased
- 2019-04-08 EP EP19720390.4A patent/EP3714337B1/de not_active Not-in-force
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019197324A1 (de) | 2019-10-17 |
| DE102018205660A1 (de) | 2019-10-17 |
| EP3714337B1 (de) | 2021-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AT519491A1 (de) | Verfahren zur Optimierung eines Prozessoptimierungssystems und Verfahren zum simulieren eines Formgebungsprozesses | |
| EP1623284B1 (de) | Verfahren zur optimierung von fahrzeugen und von motoren zum antrieb solcher fahrzeuge | |
| WO2020187563A1 (de) | Verfahren zum trainieren wenigstens eines algorithmus für ein steuergerät eines kraftfahrzeugs, computerprogrammprodukt, kraftfahrzeug sowie system | |
| DE102005026040A1 (de) | Parametrierung eines Simulations-Arbeitsmodells | |
| DE10231675B4 (de) | Simulationssystem für die Maschinensimulation und Datenausgabe von Steuerdaten für ein Automatisierungssystem | |
| WO2021058223A1 (de) | Verfahren zur effizienten, simulativen applikation automatisierter fahrfunktionen | |
| DE102019134053A1 (de) | Verfahren zur kontinuierlichen Absicherung im Fahrversuch applizierter automatisierter Fahrfunktionen | |
| DE102020001541A1 (de) | Verfahren zur Transformation erfasster Sensordaten aus einer ersten Datendomäne in eine zweite Datendomäne | |
| EP3499470A1 (de) | Verfahren zur zustandsbasierten instandhaltung einer zugangsvorrichtung | |
| EP3714337A1 (de) | Simulieren von statistisch modellierten sensordaten | |
| EP3979009A1 (de) | Erzeugen eines vereinfachten modells für xil-systeme | |
| DE10046742A1 (de) | Vorrichtung und Verfahren für ein Fahrzeugentwurfssytem | |
| EP2517129B1 (de) | Verfahren und prozessrechner zur berechnung der zustandsgrössen eines hybriden differential-algebraischen prozessmodells | |
| DE102020213016A1 (de) | Computer-implementiertes Verfahren und Vorrichtung zum Ermitteln einer Faserorientierung eines faserverstärkten Spritzgießbauteils | |
| DE102020121937A1 (de) | Verfahren zur computerimplementierten Simulation einer virtuellen Hand | |
| DE102021208472B3 (de) | Computerimplementiertes Verfahren zum Trainieren eines Machine-Learning-Modells für ein Fahrzeug oder einen Roboter | |
| DE102020203292A1 (de) | Verfahren und Vorrichtung zum Durchführen einer Crashsimulation | |
| DE102019114049A1 (de) | Verfahren zur Validierung eines Fahrerassistenzsystems mithilfe von weiteren generierten Testeingangsdatensätzen | |
| EP3521949A1 (de) | Vorrichtung zum simulieren einer gesteuerten maschine oder anlage sowie verfahren | |
| EP3553679A1 (de) | Verfahren zur computergestützten fehlerdiagnose für ein technisches system | |
| DE10325513B4 (de) | Verfahren und Vorrichtung zum Erstellen eines Verhaltensaspekts einer Schaltung zur formalen Verifikation | |
| WO2019057284A1 (de) | Automatisierbares generieren von fähigkeiten von produktionseinheiten | |
| DE102019132624A1 (de) | Verfahren, Vorrichtung, Computerprogramm und computerlesbares Speichermedium zum Erstellen eines Motion Cueing Algorithmus | |
| DE102019216676A1 (de) | Prognose eines Messwerts einer Messgröße eines technischen Systems | |
| EP2450814A2 (de) | Verfahren zur Erzeugung eines Anregungsprofils und Verfahren zur Bereitstellung von Kräften und Momenten zur Anregung von Kraftfahrzeugen |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20200623 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| AX | Request for extension of the european patent |
Extension state: BA ME |
|
| GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: GRANT OF PATENT IS INTENDED |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| INTG | Intention to grant announced |
Effective date: 20210625 |
|
| GRAS | Grant fee paid |
Free format text: ORIGINAL CODE: EPIDOSNIGR3 |
|
| GRAA | (expected) grant |
Free format text: ORIGINAL CODE: 0009210 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE PATENT HAS BEEN GRANTED |
|
| AK | Designated contracting states |
Kind code of ref document: B1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| REG | Reference to a national code |
Ref country code: GB Ref legal event code: FG4D Free format text: NOT ENGLISH |
|
| REG | Reference to a national code |
Ref country code: CH Ref legal event code: EP |
|
| REG | Reference to a national code |
Ref country code: DE Ref legal event code: R096 Ref document number: 502019002515 Country of ref document: DE |
|
| REG | Reference to a national code |
Ref country code: IE Ref legal event code: FG4D Free format text: LANGUAGE OF EP DOCUMENT: GERMAN |
|
| REG | Reference to a national code |
Ref country code: AT Ref legal event code: REF Ref document number: 1438618 Country of ref document: AT Kind code of ref document: T Effective date: 20211115 |
|
| REG | Reference to a national code |
Ref country code: LT Ref legal event code: MG9D |
|
| REG | Reference to a national code |
Ref country code: NL Ref legal event code: MP Effective date: 20211013 |
|
| PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: RS Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 Ref country code: LT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 Ref country code: FI Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 Ref country code: BG Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20220113 |
|
| PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: IS Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20220213 Ref country code: SE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 Ref country code: PT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20220214 Ref country code: PL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 Ref country code: NO Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20220113 Ref country code: NL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 Ref country code: LV Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 Ref country code: HR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 Ref country code: GR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20220114 Ref country code: ES Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 |
|
| REG | Reference to a national code |
Ref country code: DE Ref legal event code: R097 Ref document number: 502019002515 Country of ref document: DE |
|
| PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: SM Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 Ref country code: SK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 Ref country code: RO Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 Ref country code: EE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 Ref country code: DK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 Ref country code: CZ Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 |
|
| PLBE | No opposition filed within time limit |
Free format text: ORIGINAL CODE: 0009261 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT |
|
| 26N | No opposition filed |
Effective date: 20220714 |
|
| PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: AL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 |
|
| PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: SI Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 |
|
| REG | Reference to a national code |
Ref country code: CH Ref legal event code: PL |
|
| REG | Reference to a national code |
Ref country code: BE Ref legal event code: MM Effective date: 20220430 |
|
| PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MC Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 Ref country code: LU Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20220408 Ref country code: LI Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20220430 Ref country code: CH Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20220430 |
|
| PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: BE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20220430 |
|
| PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: IE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20220408 |
|
| PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: IT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 |
|
| PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: FR Payment date: 20230421 Year of fee payment: 5 Ref country code: DE Payment date: 20230619 Year of fee payment: 5 |
|
| GBPC | Gb: european patent ceased through non-payment of renewal fee |
Effective date: 20230408 |
|
| PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: GB Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20230408 |
|
| PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: GB Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20230408 |
|
| PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 Ref country code: CY Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 |
|
| PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: HU Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT; INVALID AB INITIO Effective date: 20190408 |
|
| PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: TR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 |
|
| PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211013 |
|
| REG | Reference to a national code |
Ref country code: DE Ref legal event code: R119 Ref document number: 502019002515 Country of ref document: DE |
|
| PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: DE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20241105 |
|
| PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: FR Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20240430 |
|
| PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: FR Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20240430 Ref country code: DE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20241105 |
|
| REG | Reference to a national code |
Ref country code: AT Ref legal event code: MM01 Ref document number: 1438618 Country of ref document: AT Kind code of ref document: T Effective date: 20240408 |
|
| PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: AT Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20240408 |
|
| PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: AT Payment date: 20260410 Year of fee payment: 5 |